gold
SELECT T2.Description FROM transactions_1k AS T1 INNER JOIN products AS T2 ON T1.ProductID = T2.ProductID ORDER BY T1.Amount DESC LIMIT 5
- T1.Amount
- descending
sha256:32a20ede3c2177d506fc317ff51daafc2448991653e7f8285e7bdeda19cd1e01
R-ORD GOLD-ONLY duplicate-full-row
debit_card_specializing · dev_20251106-00000-of-00001 from https://huggingface.co/datasets/birdsql/bird_sql_dev_20251106/resolve/3c11fb193e5439b338e23677fa0aae11e8b85db9/data/dev_20251106-00000-of-00001.json (commit 3c11fb19, downloaded 2026-09-07)
Which are the top five best selling products? Please state the full name of them.
the hint the set supplies: Description of products contains full name
This question was audited without a prediction beside it, so there is nothing to compare the gold with. The probes below read the gold alone.
SELECT T2.Description FROM transactions_1k AS T1 INNER JOIN products AS T2 ON T1.ProductID = T2.ProductID ORDER BY T1.Amount DESC LIMIT 5
sha256:32a20ede3c2177d506fc317ff51daafc2448991653e7f8285e7bdeda19cd1e01
from evidence-gold.json, 5 rows
| DescriptionTEXT |
|---|
| Nafta |
| Diesel + |
| Nafta |
| Nafta |
| Nafta |
A smell is a mechanical reason to read this gold statement again. It is a heuristic: it does not state that the statement is wrong, and a maintainer decides.
this statement orders by a text column holding only numbers, and ordering it as a number gives a different answer, so the gold may be sorting 9.5 above 10
no ORDER BY key resolves to a text column
{
"heuristic": true,
"reason": "no ORDER BY key resolves to a text column",
"keys": [
{
"key": "T1.Amount",
"column": "transactions_1k.Amount",
"declared_type": "INTEGER",
"not_applicable": "the column is not declared as text"
}
]
}
this statement cuts its result at a LIMIT that does not decide which rows come back, so a different but equally correct statement can return other rows and score zero
{
"heuristic": true,
"cut": 5,
"offset": 0,
"distinct_kept": false,
"unbounded_sql": "SELECT T2.Description, T1.Amount AS attestql_ordering_key_0 FROM transactions_1k AS T1 INNER JOIN products AS T2 ON T1.ProductID = T2.ProductID ORDER BY T1.Amount DESC",
"unbounded_rows": 1000,
"projected_columns": [
"Description"
],
"ordering_key_columns": [
"attestql_ordering_key_0"
],
"ordering_keys": [
{
"key": "T1.Amount",
"direction": "desc",
"nulls": "last",
"nulls_first_in_effect": false,
"returned_rows_null_in_this_key": 0,
"fires": false
}
],
"case": null
}
rerun over the same rows in another physical order this statement gives another answer, so its result depends on how the rows are stored and not only on the data
{
"heuristic": true,
"rule": "R-ORD",
"baseline_result_hash": "sha256:32a20ede3c2177d506fc317ff51daafc2448991653e7f8285e7bdeda19cd1e01",
"baseline_result": {
"columns": [
{
"name": "Description",
"declared_type": "TEXT"
}
],
"row_count": 5,
"truncated": false,
"rows_shown": 5,
"rows": [
[
{
"type": "str",
"value": "Nafta"
}
],
[
{
"type": "str",
"value": "Diesel +"
}
],
[
{
"type": "str",
"value": "Nafta"
}
],
[
{
"type": "str",
"value": "Nafta"
}
],
[
{
"type": "str",
"value": "Nafta"
}
]
],
"result_hash": "sha256:32a20ede3c2177d506fc317ff51daafc2448991653e7f8285e7bdeda19cd1e01"
},
"planner_statistics": {},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"transactions_1k",
"products"
],
"tables_not_shuffled": [],
"tables_skipped_for_size": {
"yearmonth": 383282
},
"tables_not_reached_by_a_copy": {}
},
"shuffled_copies": {
"run": true,
"verdict": "equal",
"differs": false,
"result_hash": "sha256:32a20ede3c2177d506fc317ff51daafc2448991653e7f8285e7bdeda19cd1e01",
"result": {
"columns": [
{
"name": "Description",
"declared_type": "TEXT"
}
],
"row_count": 5,
"truncated": false,
"rows_shown": 5,
"rows": [
[
{
"type": "str",
"value": "Nafta"
}
],
[
{
"type": "str",
"value": "Diesel +"
}
],
[
{
"type": "str",
"value": "Nafta"
}
],
[
{
"type": "str",
"value": "Nafta"
}
],
[
{
"type": "str",
"value": "Nafta"
}
]
],
"result_hash": "sha256:32a20ede3c2177d506fc317ff51daafc2448991653e7f8285e7bdeda19cd1e01"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}
this statement returns the same whole row more than once and never says DISTINCT, so a statement answering the same question once per row disagrees on multiplicity alone
from smells.json, 1 row
| Nafta |
{
"heuristic": true,
"rows": 5,
"distinct_rows": 2,
"repeated_rows": 1,
"largest_repeat": 4,
"result_bounded": false,
"distinct_stated": false,
"set_operation": false,
"repeats_of_the_rows_shown": [
4
]
}
SELECT T2.Description FROM transactions_1k AS T1 INNER JOIN products AS T2 ON T1.ProductID = T2.ProductID ORDER BY T1.Amount DESC LIMIT 5
result_hash sha256:32a20ede3c2177d506fc317ff51daafc2448991653e7f8285e7bdeda19cd1e01 recomputed from this JSON: match
record_hash sha256:e24548d56c85ea5a9c78ebb67e7355f6e7fae72c47f5ef0f22acb7c8db93f392 recomputed from this JSON: match
from evidence-gold.json, 5 rows
| DescriptionTEXT |
|---|
| Nafta |
| Diesel + |
| Nafta |
| Nafta |
| Nafta |
re-run this statement read-only against SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/dev/dev_databases/debit_card_specializing/debit_card_specializing.sqlite | size=34635776 under the session settings and over the data this record's fixture digest names, and compare the two results under R-ORD